Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 147 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0320. Min Act: -0.0003

Data Index: 381803 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0302. Min Act: -0.0001

Data Index: 637245 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1060685 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0278. Min Act: -0.0003

Data Index: 1185358 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0277. Min Act: -0.0003

Data Index: 118793 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0282. Min Act: -0.0002

Data Index: 463472 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0271. Min Act: -0.0003

Data Index: 705038 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0276. Min Act: -0.0002

Data Index: 161708 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0278. Min Act: -0.0002

Data Index: 680480 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0267. Min Act: -0.0002

Data Index: 969390 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1235855 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0264. Min Act: -0.0004

Data Index: 331483 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0268. Min Act: -0.0003

Data Index: 291131 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0274. Min Act: -0.0003

Data Index: 425027 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1222233 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0260. Min Act: -0.0002

Data Index: 138880 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1084722 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0248. Min Act: -0.0003

Data Index: 184891 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0257. Min Act: -0.0004

Data Index: 960874 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1221051 (C4 (Web Text))

Max Activating Token Index: 320